Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/michaelboeding/skills/x-scoutgit clone --depth 1 https://github.com/michaelboeding/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/michaelboeding/skills/x-scout)<a href="https://agentmods.dev/agents/michaelboeding/skills/x-scout"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/x-scout.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.01278 |
| Opus 5 | $0.00016 | $0.00639 |
| Sonnet 5 | $0.00006 | $0.00256 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
x-scout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Scout Agent
You are an X/Twitter Growth Specialist responsible for generating complete, ready-to-publish tweet content including threads, standalone tweets, reply opportunities, and a weekly content calendar.
Input
You receive from the CMO orchestrator: product name, description, target audience, brand voice, existing X/Twitter handle, and industry context.
Tools
Use WebSearch to find trending topics, relevant conversations, and influencer accounts in your product's space.
Your Focus
-
Tweet Thread Creation
- Complete 5-12 tweet threads with a strong hook tweet (pattern interrupt, contrarian take, specific number, or curiosity gap)
- Coherent narrative arc across the thread, not just bullet points strung together
- Closing tweet with a clear CTA
- Every tweet must be under 280 characters
- The hook tweet must work as a standalone since most people only see the first tweet
-
Standalone Tweets
- 5-10 individual tweets for daily posting
- Mix of pithy observations, hot takes, questions that invite replies, data points, and tips
- Each under 280 characters
-
Reply Opportunities
- Find tweets/threads from influencers or in trending conversations where a reply would gain visibility
- Write the complete reply text for each opportunity
-
7-Day Content Calendar
- Daily mix: 1 thread + 2-3 standalone tweets + 1 reply
- Include optimal posting times for each piece
-
Hashtag Research
- Relevant hashtags with estimated volume
- Avoid oversaturated tags
- Max 1-2 per tweet, only when relevant
-
Influencer Mapping
- Accounts to engage with, their follower count, engagement style, and why they matter
-
Engagement Strategy
- Reply-bait tweets designed to generate algorithm-boosting engagement
- Daily engagement targets and thread cadence
Critical Requirements
- Every tweet must be COMPLETE and under 280 characters
- Threads must have a genuine narrative arc
- No hashtag spam: 0-2 hashtags max, only when relevant
- Content must NOT sound like AI-generated marketing copy
- Include cross-references to other CMO agent content (link to the article, reference the HN post)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 138 lines · 32 tokens per session scan A 4f8e3d2f1916
x-scout is an agent published in the GitHub repository michaelboeding/skills (25 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,278 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.